EP 3504034 A1 20190703 - DEEP REINFORCEMENT LEARNING FOR ROBOTIC MANIPULATION
Title (en)
DEEP REINFORCEMENT LEARNING FOR ROBOTIC MANIPULATION
Title (de)
TIEFENVERSTÄRKUNGSLERNEN FÜR ROBOTISCHE MANIPULATION
Title (fr)
APPRENTISSAGE DE RENFORCEMENT PROFOND POUR LA MANIPULATION ROBOTIQUE
Publication
Application
Priority
- US 201662395340 P 20160915
- US 2017051646 W 20170914
Abstract (en)
[origin: WO2018053187A1] Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.
IPC 8 full level
B25J 9/16 (2006.01); G05B 13/02 (2006.01); G06N 3/00 (2006.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01)
CPC (source: CN EP KR US)
B25J 9/161 (2013.01 - EP KR US); B25J 9/163 (2013.01 - CN EP KR US); B25J 9/1664 (2013.01 - CN EP KR US); G05B 13/027 (2013.01 - EP KR US); G05B 13/042 (2013.01 - CN); G05B 19/042 (2013.01 - US); G06N 3/008 (2013.01 - CN EP KR US); G06N 3/045 (2023.01 - EP KR US); G06N 3/08 (2013.01 - EP KR US); G06N 3/084 (2013.01 - CN); G05B 2219/32335 (2013.01 - US); G05B 2219/33033 (2013.01 - EP KR US); G05B 2219/33034 (2013.01 - EP KR US); G05B 2219/39001 (2013.01 - US); G05B 2219/39298 (2013.01 - EP KR US); G05B 2219/40499 (2013.01 - EP KR US)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2018053187 A1 20180322; CN 109906132 A 20190618; CN 109906132 B 20220809; CN 115338859 A 20221115; DE 202017105598 U1 20180524; EP 3504034 A1 20190703; JP 2019529135 A 20191017; JP 6721785 B2 20200715; KR 102211012 B1 20210203; KR 20190040506 A 20190418; US 11400587 B2 20220802; US 11897133 B2 20240213; US 2019232488 A1 20190801; US 2022388159 A1 20221208; US 2024131695 A1 20240425
DOCDB simple family (application)
US 2017051646 W 20170914; CN 201780067067 A 20170914; CN 202210871601 A 20170914; DE 202017105598 U 20170915; EP 17772579 A 20170914; JP 2019514301 A 20170914; KR 20197009013 A 20170914; US 201716333482 A 20170914; US 202217878186 A 20220801; US 202318526443 A 20231201